今日内容:
注意: selenium驱动的浏览器是干净的，没有任何缓存。
1、selenium剩余用法
2、selenium万能登录破解
3、selenium爬取京东商品信息
4、破解极验滑动验证码
Xpath语法:
今日作业:
1、总结课堂知识点，写博客
2、爬取京东商品信息
3、滑动验证（提高题）
一、自动登录抽屉新热榜
from selenium import webdriver import time driver = webdriver.Chrome(r'D:BaiduNetdiskDownloadchromedriver_win32chromedriver.exe') # 把窗口转成全屏 driver.maximize_window() try: driver.get('https://dig.chouti.com/') driver.implicitly_wait(10) time.sleep(5) # 1、点击登录 login_btn = driver.find_element_by_id('login_btn') login_btn.click() time.sleep(2) # 2、输入用户名 phone = driver.find_element_by_class_name('login-phone') phone.send_keys('15622792660') # 3、输入密码 pwd = driver.find_element_by_class_name('pwd-password-input') pwd.send_keys('kermit46709394') # 4、确认登录 login_submit = driver.find_element_by_class_name('btn-large') login_submit.click() time.sleep(20) # 捕获异常并打印 except Exception as e: print(e) finally: driver.close()
二、 selenium选择器之Xpath
from selenium import webdriver driver = webdriver.Chrome(r'D:BaiduNetdiskDownloadchromedriver_win32chromedriver.exe') try: # 隐式等待: 写在get请求前 driver.implicitly_wait(5) driver.get('https://doc.scrapy.org/en/latest/_static/selectors-sample1.html') # 显式等待: 写在get请求后 # wait.until(...) ''' <html> <head> <base href='http://example.com/' /> <title>Example website</title> </head> <body> <div id='images'> <a href='image1.html'>Name: My image 1 <br /><img src='image1_thumb.jpg' /></a> <a href='image2.html'>Name: My image 2 <br /><img src='image2_thumb.jpg' /></a> <a href='image3.html'>Name: My image 3 <br /><img src='image3_thumb.jpg' /></a> <a href='image4.html'>Name: My image 4 <br /><img src='image4_thumb.jpg' /></a> <a href='image5.html'>Name: My image 5 <br /><img src='image5_thumb.jpg' /></a> </div> </body> </html> ''' # 根据xpath语法查找元素 # / 从根节点开始找第一个 html = driver.find_element_by_xpath('/html') # html = driver.find_element_by_xpath('/head') # 报错 print(html.tag_name) # // 从根节点开始找任意一个节点 div = driver.find_element_by_xpath('//div') print(div.tag_name) # @ # 查找id为images的div节点 div = driver.find_element_by_xpath('//div[@id="images"]') print(div.tag_name) print(div.text) # 找到第一个a节点 a = driver.find_element_by_xpath('//a') print(a.tag_name) # 找到所有a节点 a_s = driver.find_elements_by_xpath('//a') print(a_s) # 找到第一个a节点的href属性 # get_attribute:获取节点中某个属性 a = driver.find_element_by_xpath('//a').get_attribute('href') print(a) finally: driver.close()
三、selenium剩余操作
'''''' ''' 点击、清除操作 ''' # from selenium import webdriver # from selenium.webdriver.common.keys import Keys # import time # # driver = webdriver.Chrome(r'D:BaiduNetdiskDownloadchromedriver_win32chromedriver.exe') # # try: # driver.implicitly_wait(10) # # 1、往jd发送请求 # driver.get('https://www.jd.com/') # # 找到输入框输入围城 # input_tag = driver.find_element_by_id('key') # input_tag.send_keys('围城') # # 键盘回车 # input_tag.send_keys(Keys.ENTER) # time.sleep(2) # # 找到输入框输入墨菲定律 # input_tag = driver.find_element_by_id('key') # input_tag.clear() # input_tag.send_keys('墨菲定律') # # 找到搜索按钮点击搜索 # button = driver.find_element_by_class_name('button') # button.click() # time.sleep(10) # # finally: # driver.close() ''' 获取cookies （了解） ''' # from selenium import webdriver # import time # # driver = webdriver.Chrome(r'D:BaiduNetdiskDownloadchromedriver_win32chromedriver.exe') # # try: # driver.implicitly_wait(10) # driver.get('https://www.zhihu.com/explore') # print(driver.get_cookies()) # # time.sleep(10) # finally: # driver.close() ''' 选项卡 ''' #选项卡管理：切换选项卡，有js的方式windows.open,有windows快捷键： # ctrl+t等，最通用的就是js的方式 # import time # from selenium import webdriver # # browser = webdriver.Chrome() # try: # browser.get('https://www.baidu.com') # # # execute_script: 执行javascrpit代码 # # 弹窗操作 # # browser.execute_script('alert("tank")') # # 新建浏览器窗口 # browser.execute_script( # ''' # window.open(); # ''' # ) # time.sleep(1) # print(browser.window_handles) # 获取所有的选项卡 # # 切换到第二个窗口 # # 新: # browser.switch_to.window(browser.window_handles[1]) # # 旧: # # browser.switch_to_window(browser.window_handles[1]) # # # 第二个窗口往淘宝发送请求 # browser.get('https://www.taobao.com') # time.sleep(5) # # # 切换到第一个窗口 # browser.switch_to_window(browser.window_handles[0]) # browser.get('https://www.sina.com.cn') # # time.sleep(10) # finally: # browser.close() ''' ActionChangs动作链 ''' # from selenium import webdriver # from selenium.webdriver import ActionChains # import time # # driver = webdriver.Chrome() # driver.implicitly_wait(10) # driver.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable') # # try: # # # driver.switch_to_frame('iframeResult') # # 切换到id为iframeResult的窗口内 # driver.switch_to.frame('iframeResult') # # # 源位置 # draggable = driver.find_element_by_id('draggable') # # # 目标位置 # droppable = driver.find_element_by_id('droppable') # # # 调用ActionChains，必须把驱动对象传进去 # # 得到一个动作链对象，复制给一个变量 # actions = ActionChains(driver) # # # 方式一: 机器人 # # 瞬间把源图片位置秒移到目标图片位置 # # actions.drag_and_drop(draggable, droppable) # 编写一个行为 # # actions.perform() # 执行编写好的行为 # # # # 方式二: 模拟人的行为 # source = draggable.location['x'] # target = droppable.location['x'] # print(source, target) # # distance = target - source # print(distance) # # # perform：每个动作都要调用perform执行 # # # 点击并摁住源图片 # ActionChains(driver).click_and_hold(draggable).perform() # # s = 0 # while s < distance: # # 执行位移操作 # ActionChains(driver).move_by_offset(xoffset=2, yoffset=0).perform() # s += 2 # # # 释放动作链 # ActionChains(driver).release().perform() # # time.sleep(10) # # # finally: # driver.close() ''' 前进、后退 ''' # from selenium import webdriver # import time # # driver = webdriver.Chrome() # # try: # driver.implicitly_wait(10) # driver.get('https://www.jd.com/') # driver.get('https://www.baidu.com/') # driver.get('https://www.cnblogs.com/') # # time.sleep(2) # # # 回退操作 # driver.back() # time.sleep(1) # # 前进操作 # driver.forward() # time.sleep(1) # driver.back() # time.sleep(10) # # finally: # driver.close()
四、破解登录
from selenium import webdriver from selenium.webdriver import ChromeOptions import time r''' 步骤: 1、打开文件的查看，显示隐藏文件 2、找到C:UsersadministortraAppDataLocalGoogleChromeUser Data 删除Default文件 3、重新打开浏览器，并登陆百度账号 - 此时会创建一个新的Default缓存文件 4、添加cookies 5、关闭谷歌浏览器后执行程序 ''' # 获取options对象，参数对象 options = ChromeOptions() # 获取cookies保存路径 # 'C:UsersadministortraAppDataLocalGoogleChromeUser Data' profile_directory = r'--user-data-dir=C:UsersadministortraAppDataLocalGoogleChromeUser Data' # 添加用户信息目录 options.add_argument(profile_directory) # 把参数加载到当前驱动中 chrome_options默认参数，用来接收options对象 driver = webdriver.Chrome(chrome_options=options) try: driver.implicitly_wait(10) driver.get('https://www.baidu.com/') ''' BDUSS:***** ''' # 添加用户cookies信息 # name、value必须小写 driver.add_cookie({"name": "BDUSS", "value": "用户session字符串"}) # 刷新操作 driver.refresh() time.sleep(10) finally: driver.close()
五、04 selenium爬取京东商品信息
# '''''' # ''' # 爬取京东商品信息: # 请求url: # https://www.jd.com/ # 提取商品信息: # 1.商品详情页 # 2.商品名称 # 3.商品价格 # 4.评价人数 # 5.商品商家 # ''' # from selenium import webdriver # from selenium.webdriver.common.keys import Keys # import time # # driver = webdriver.Chrome() # # try: # driver.implicitly_wait(10) # # 1、往京东主页发送请求 # driver.get('https://www.jd.com/') # # # 2、输入商品名称，并回车搜索 # input_tag = driver.find_element_by_id('key') # input_tag.send_keys('macbook') # input_tag.send_keys(Keys.ENTER) # time.sleep(2) # # # 通过JS控制滚轮滑动获取所有商品信息 # js_code = ''' # window.scrollTo(0,5000); # ''' # driver.execute_script(js_code) # 执行js代码 # # # 等待数据加载 # time.sleep(2) # # # 3、查找所有商品div # # good_div = driver.find_element_by_id('J_goodsList') # good_list = driver.find_elements_by_class_name('gl-item') # n = 1 # for good in good_list: # # 根据属性选择器查找 # # 商品链接 # good_url = good.find_element_by_css_selector( # '.p-img a').get_attribute('href') # # # 商品名称 # good_name = good.find_element_by_css_selector( # '.p-name em').text.replace(" ", "--") # # # 商品价格 # good_price = good.find_element_by_class_name( # 'p-price').text.replace(" ", ":") # # # 评价人数 # good_commit = good.find_element_by_class_name( # 'p-commit').text.replace(" ", " ") # # # 商品商家 # good_from = good.find_element_by_class_name( # 'J_im_icon').text.replace(" ", " ") # # good_content = f''' # 商品链接: {good_url} # 商品名称: {good_name} # 商品价格: {good_price} # 评价人数: {good_commit} # 商品商家: {good_from} # # ''' # print(good_content) # with open('jd.txt', 'a', encoding='utf-8') as f: # f.write(good_content) # # next_tag = driver.find_element_by_link_text('下一页') # # next_tag.click() # # time.sleep(10) # # # finally: # driver.close() '''''' ''' 爬取京东商品信息: 请求url: https://www.jd.com/ 提取商品信息: 1.商品详情页 2.商品名称 3.商品价格 4.评价人数 5.商品商家 ''' from selenium import webdriver from selenium.webdriver.common.keys import Keys import time def get_good(driver): try: # 通过JS控制滚轮滑动获取所有商品信息 js_code = ''' window.scrollTo(0,5000); ''' driver.execute_script(js_code) # 执行js代码 # 等待数据加载 time.sleep(2) # 3、查找所有商品div # good_div = driver.find_element_by_id('J_goodsList') good_list = driver.find_elements_by_class_name('gl-item') n = 1 for good in good_list: # 根据属性选择器查找 # 商品链接 good_url = good.find_element_by_css_selector( '.p-img a').get_attribute('href') # 商品名称 good_name = good.find_element_by_css_selector( '.p-name em').text.replace(" ", "--") # 商品价格 good_price = good.find_element_by_class_name( 'p-price').text.replace(" ", ":") # 评价人数 good_commit = good.find_element_by_class_name( 'p-commit').text.replace(" ", " ") good_content = f''' 商品链接: {good_url} 商品名称: {good_name} 商品价格: {good_price} 评价人数: {good_commit} ''' print(good_content) with open('jd.txt', 'a', encoding='utf-8') as f: f.write(good_content) next_tag = driver.find_element_by_class_name('pn-next') next_tag.click() time.sleep(2) # 递归调用函数 get_good(driver) time.sleep(10) finally: driver.close() if __name__ == '__main__': good_name = input('请输入爬取商品信息:').strip() driver = webdriver.Chrome() driver.implicitly_wait(10) # 1、往京东主页发送请求 driver.get('https://www.jd.com/') # 2、输入商品名称，并回车搜索 input_tag = driver.find_element_by_id('key') input_tag.send_keys(good_name) input_tag.send_keys(Keys.ENTER) time.sleep(2) get_good(driver)
作业：破解极限滑动验证
'''''' ''' 破解极验滑动验证 博客园登录url: https://account.cnblogs.com/signin?returnUrl=https%3A%2F%2Fwww.cnblogs.com%2F 1、输入用户名与密码，并点击登录 2、弹出滑动验证，获取有缺口与完整的图片 3、通过像素点进行比对，获取滑动位移距离 4、模拟人的行为轨迹 5、开始滑动 ''' from selenium import webdriver # 用来驱动浏览器的 from selenium.webdriver import ActionChains # 破解滑动验证码的时候用的 可以拖动图片 import time from PIL import Image # pip3 install pillow import random option = webdriver.ChromeOptions() option.add_argument('disable-infobars') driver = webdriver.Chrome(chrome_options=option) def get_snap(driver): # selenium自带的截图网页全屏图片 driver.save_screenshot('snap.png') img = driver.find_element_by_class_name('geetest_canvas_img') left = img.location['x'] upper = img.location['y'] right = left + img.size['width'] lower = upper + img.size['height'] # print(left, upper, right, lower) img_obj = Image.open('snap.png') # 对屏幕进行截取,获取滑动验证图片 image = img_obj.crop((left, upper, right, lower)) return image def get_image1(driver): time.sleep(0.2) js_code = ''' var x = document.getElementsByClassName('geetest_canvas_fullbg')[0].style.display="block"; console.log(x) ''' time.sleep(1) driver.execute_script(js_code) # 截取图片 img_obj = get_snap(driver) return img_obj def get_image2(driver): time.sleep(0.2) js_code = ''' var x = document.getElementsByClassName('geetest_canvas_fullbg')[0].style.display="none"; console.log(x) ''' driver.execute_script(js_code) time.sleep(1) # 截取图片 img_obj = get_snap(driver) return img_obj def get_distance(image1, image2): # 初始值 start = 60 # 滑块色差 color_num = 60 for x in range(start, image1.size[0]): for y in range(image1.size[1]): rgb1 = image1.load()[x, y] rgb2 = image2.load()[x, y] r = abs(rgb1[0] - rgb2[0]) g = abs(rgb1[1] - rgb2[1]) b = abs(rgb1[2] - rgb2[2]) if not (r < color_num and g < color_num and b < color_num): return x - 7 def get_stacks(distance): distance += 20 ''' 匀加速减速运行 v = v0 + a * t 位移: s = v * t + 0.5 * a * (t**2) ''' # 初速度 v0 = 0 # 加减速度列表 a_list = [3, 4, 5] # 时间 t = 0.2 # 初始位置 s = 0 # 向前滑动轨迹 forward_stacks = [] mid = distance * 3 / 5 while s < distance: if s < mid: a = a_list[random.randint(0, 2)] else: a = -a_list[random.randint(0, 2)] v = v0 stack = v * t + 0.5 * a * (t ** 2) # 每次拿到的位移 stack = round(stack) s += stack v0 = v + a * t forward_stacks.append(stack) back_stacks = [-1, -1, -2, -3, -2, -3, -2, -2, -3, -1] return {'forward_stacks': forward_stacks, 'back_stacks': back_stacks} def main(): try: driver.get('https://passport.cnblogs.com/user/signin') driver.implicitly_wait(5) # 1.输入用户名与密码,点击登录 username = driver.find_element_by_id('LoginName') password = driver.find_element_by_id('Password') login_button = driver.find_element_by_class_name('ladda-label') time.sleep(1) username.send_keys('_tank_') time.sleep(1) password.send_keys('k46709394.') # 这里需要等待账号密码输入完毕后再点击登录按钮，否则的不弹框 time.sleep(1) login_button.click() # time.sleep(3) # 2.点击滑动验证按钮,获取图片 geetest_button = driver.find_element_by_class_name('geetest_slider_button') geetest_button.click() time.sleep(0.2) # 3.针对完整的图片进行截取 image1 = get_image1(driver) # 4.针对有缺口的图片进行截取 image2 = get_image2(driver) # 5.对比两张图片,获取滑动距离 distance = get_distance(image1, image2) # 6.模拟人为滑动轨迹 stacks = get_stacks(distance) # 7.根据滑动轨迹进行滑动 forward_stacks = stacks['forward_stacks'] back_stacks = stacks['back_stacks'] slider_button = driver.find_element_by_class_name('geetest_slider_button') time.sleep(0.2) ActionChains(driver).click_and_hold(slider_button).perform() time.sleep(0.2) for forward_stack in forward_stacks: ActionChains(driver).move_by_offset(xoffset=forward_stack, yoffset=0).perform() time.sleep(0.1) for back_stack in back_stacks: ActionChains(driver).move_by_offset(xoffset=back_stack, yoffset=0).perform() time.sleep(0.1) time.sleep(0.2) ActionChains(driver).move_by_offset(xoffset=5, yoffset=0).perform() ActionChains(driver).move_by_offset(xoffset=-5, yoffset=0).perform() ActionChains(driver).release().perform() time.sleep(50) finally: driver.close() if __name__ == '__main__': main()